Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4562 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0480. Min Range: -1.0480

Max Act: 1.0480. Min Act: -0.0000

Data Index: 767715 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8744. Min Act: -0.0000

Data Index: 220469 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9721. Min Act: -0.0000

Data Index: 431324 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9808. Min Act: -0.0000

Data Index: 103986 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9261. Min Act: -0.0000

Data Index: 352561 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 1.0480. Min Range: -1.0480

Max Act: 1.0378. Min Act: -0.0000

Data Index: 644259 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1216942 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9322. Min Act: -0.0000

Data Index: 985996 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9288. Min Act: -0.0000

Data Index: 56673 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9572. Min Act: -0.0000

Data Index: 286089 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8140. Min Act: -0.0000

Data Index: 391124 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9472. Min Act: -0.0000

Data Index: 471370 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8996. Min Act: -0.0000

Data Index: 122486 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1172152 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8523. Min Act: -0.0000

Data Index: 820649 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8245. Min Act: -0.0000

Data Index: 392845 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8919. Min Act: -0.0000

Data Index: 968875 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8927. Min Act: -0.0000

Data Index: 702886 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1186810 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1228574 (C4 (Web Text))

Max Activating Token Index: 102